Identity-preserving image generation becomes increasingly unreliable when a scene must contain many specified people. Beyond retaining each identity, the model must bind every reference to a distinct person and location, while training-time identity losses must establish correspondence among several noisy predicted faces.
To address this, researchers at Hugging Face introduce WithEveryone, a unified framework for generating group images with up to ten reference identities. The system injects each selected identity as an addressed token, predicts a structured identity–layout plan, and renders the plan as a visual condition.
Its key objective, Layout-Grounded ID Loss, uses annotated face regions to supervise the intended identities directly, avoiding unstable embedding-based face matching. Additionally, ID Representation Forcing trains a prediction for each identity before image synthesis.
On an identity-disjoint benchmark, WithEveryone achieves the highest target-context identity similarity, improving face similarity from 0.462 (GPT-Image-2) to 0.499, while reducing copy-paste artifacts from 0.169 to 0.055. It covers 97.3% of requested identities with a duplicate rate of only 2.8%.
These results demonstrate that explicit identity–layout grounding enables identity-preserving generation to scale to larger groups without relying on direct reference-face copying.